Abstract: Cell morphology is often used as a proxy measurement of cell status to understand cell physiology. Hence, the interpretation of cell dynamic morphology is a meaningful task in biomedical research. Mouse lymphocytes were collected to observe the dynamic morphology, and two datasets were thus set up. Local temporal feature was proposed to consider spatial heterogeneity and temporal regularity of cell dynamic morphology. The local temporal feature was applied to the video data of cell dynamic morphology, and compared with existing methods. Experiment results show that, the local temporal feature can outperform the existing methods and provide remarkable advances in the accuracy and robustness of the classification on both datasets.